
import pickle
import numpy as np
import pandas as pd
import plotly.express as px
from sklearn.manifold import TSNE
from scipy import stats
from sklearn.base import BaseEstimator, TransformerMixin
from sklearn.preprocessing import OneHotEncoder, FunctionTransformer, StandardScaler
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import classification_report
from sklearn.pipeline import Pipeline
from sklearn.metrics import r2_score
from xgboost import XGBRegressor
from sklearn.compose import ColumnTransformer
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.experimental import enable_halving_search_cv
from sklearn.model_selection import HalvingGridSearchCV


with open("train.pickle", "rb") as f:
    df_train = pickle.load(f)
    
with open("test.pickle", "rb") as f:
    df_test = pickle.load(f)


df_train["rating_numeric"] = df_train["rating"].map({'Negative': 0., 'Mixed': 1., 'Mostly Positive': 2., 'Positive': 3., 'Very Positive': 4.}).astype(float)
def describe_dataset(df_train):
    display(df_train)
    display(df_train.describe())
    print(f'Duplicados: {df_train[df_train.duplicated(subset=["name"])].shape[0]}')
    
describe_dataset(df_train)

Duplicados: 0


def show_correlations(df_train):
    corr = df_train.corr()
    display(corr)
    px.imshow(corr)

show_correlations(df_train)


def histograms_categorical(df_train):
    developer = px.histogram(df_train, x="developer").update_xaxes(categoryorder='total ascending')
    publisher = px.histogram(df_train, x="publisher").update_xaxes(categoryorder='total ascending')
    developer2 = px.histogram(df_train, x="developer", y="estimated_sells", histfunc="avg").update_xaxes(categoryorder='total ascending')
    publisher2 = px.histogram(df_train, x="publisher", y="estimated_sells", histfunc="avg").update_xaxes(categoryorder='total ascending')
    developer3 = px.histogram(df_train, x="developer", y="rating_numeric", histfunc="avg").update_xaxes(categoryorder='total ascending')
    publisher3 = px.histogram(df_train, x="publisher", y="rating_numeric", histfunc="avg").update_xaxes(categoryorder='total ascending')
    developer.show()
    publisher.show()
    developer2.show()
    publisher2.show()
    developer3.show()
    publisher3.show()

histograms_categorical(df_train)


def histograms_numerical(df_train):
    es = px.histogram(df_train, x="estimated_sells")
    ra = px.histogram(df_train, x="rating_numeric")
    h1 = px.histogram(df_train, x="required_age")
    h2 = px.histogram(df_train, x="average_playtime")
    h3 = px.histogram(df_train, x="price")
    es.show()
    ra.show()
    h1.show()
    h2.show()
    h3.show()
    
histograms_numerical(df_train)


def histograms_sells(df_train):
    es1 = px.histogram(df_train, x="required_age", y="estimated_sells", histfunc="avg")
    es2 = px.histogram(df_train, x="average_playtime", y="estimated_sells", histfunc="avg")
    es3 = px.histogram(df_train, x="price", y="estimated_sells", histfunc="avg")
    es1.show()
    es2.show()
    es3.show()

histograms_sells(df_train)


def histograms_rating(df_train):
    r1 = px.histogram(df_train, x="estimated_sells", y="rating_numeric", histfunc="avg")
    r2 = px.histogram(df_train, x="price", y="rating_numeric", histfunc="avg")
    r1.show()
    r2.show()
    
histograms_rating(df_train)


def plot_tsne(X, df_train, label):
    fig = px.scatter(
        X, x=0, y=1,
        color=df_train[label], labels={'color': label}
    )
    fig.show()

def twod_proyections(df_train):
    X = TSNE(init="random", learning_rate="auto").fit_transform(df_train.select_dtypes(include=np.number))
    plot_tsne(X, df_train, "estimated_sells")
    plot_tsne(X, df_train, "rating")

twod_proyections(df_train)


def whole_exploration(df_train):
    describe_dataset(df_train)
    show_correlations(df_train)
    histograms_categorical(df_train)
    histograms_numerical(df_train)
    histograms_sells(df_train)
    histograms_rating(df_train)
    twod_proyections(df_train)


df_clean = df_train[(np.abs(stats.zscore(df_train.loc[:, ["estimated_sells", "average_playtime"]]) < 1).all(axis=1))]
print(f"Datos eliminados: {df_train.shape[0] - df_clean.shape[0]}")

Datos eliminados: 257


whole_exploration(df_clean)

Duplicados: 0


class SeparatorTransformer(BaseEstimator, TransformerMixin):
    def __init__(self, feature_name, separator=";"):
        self.feature_name = feature_name
        self.separator = ";"
    
    def fit(self, X, y = None):
        self.all_categories = set(self.separator.join(set(X[self.feature_name].values)).split(self.separator))
        self.all_categories = np.array(list(self.all_categories))
        self.ohe = OneHotEncoder(handle_unknown="ignore")
        self.ohe.fit(self.all_categories.reshape((-1, 1)))
        return self
    
    def transform(self, X, y = None):
        splitted = X[self.feature_name].str.split(";", expand=True)
        encoded = np.zeros((X.shape[0], len(self.all_categories)))
        for _, content in splitted.items():
            transformed = self.ohe.transform(content.to_numpy().reshape(-1, 1))
            encoded += transformed
        return np.asarray(encoded)


one_hot_encode_columns = ["developer", "publisher", "platforms", "categories", "genres", "tags"]
numeric_columns = ["achievements", "average_playtime", "price"]
transformers = [(f"ohe{i}", SeparatorTransformer(column), [column]) for i, column in enumerate(one_hot_encode_columns)]
transformers += [("num", StandardScaler(), numeric_columns)]
transformers += [('passthough', FunctionTransformer(lambda x: x, lambda x: x), ['english'])]
transformers += [("tfidf", TfidfVectorizer(), "short_description")]
preprocessor = ColumnTransformer(transformers=transformers)


clf_classifier = Pipeline(
    steps=[("preprocessor", preprocessor), ("classifier", RandomForestClassifier())]
)
clf_regressor = Pipeline(
    steps=[("preprocessor", preprocessor), ("regressor", XGBRegressor())]
)
X_train_c, X_test_c, y_train_c, y_test_c = train_test_split(df_clean, df_clean["rating"], test_size=0.1, random_state=1)
X_train_r, X_test_r, y_train_r, y_test_r = train_test_split(df_clean, df_clean["estimated_sells"], test_size=0.1, random_state=1)
clf_classifier.fit(X_train_c, y_train_c)
clf_regressor = clf_regressor.fit(X_train_r, y_train_r)


y_pred_c = clf_classifier.predict(X_test_c)
print(classification_report(y_test_c, y_pred_c))

                 precision    recall  f1-score   support

          Mixed       0.29      0.26      0.27       162
Mostly Positive       0.20      0.20      0.20       136
       Negative       0.50      0.31      0.38       132
       Positive       0.35      0.62      0.44       211
  Very Positive       0.78      0.17      0.28       122

       accuracy                           0.34       763
      macro avg       0.42      0.31      0.32       763
   weighted avg       0.40      0.34      0.33       763


y_pred_r = clf_regressor.predict(X_test_r)
print(r2_score(y_test_r, y_pred_r))

0.3592424872181571


y_pred_competition_r = clf_regressor.predict(df_test)


y_pred_competition_c = clf_classifier.predict(df_test)


one_hot_encode_columns = ["developer", "publisher", "categories", "genres", "tags"]
numeric_columns = ["achievements", "average_playtime", "price"]
transformers = [(f"ohe{i}", SeparatorTransformer(column), [column]) for i, column in enumerate(one_hot_encode_columns)]
transformers += [("num", StandardScaler(), numeric_columns)]
preprocessor = ColumnTransformer(transformers=transformers)
clf_classifier = Pipeline(
    steps=[("preprocessor", preprocessor), ("classifier", RandomForestClassifier())]
)
clf_regressor = Pipeline(
    steps=[("preprocessor", preprocessor), ("regressor", XGBRegressor())]
)


param_grid_clf = {"classifier__n_estimators": [50, 100, 200], "classifier__max_depth": [None, 50, 100, 200]}
gs_clf = HalvingGridSearchCV(clf_classifier, param_grid_clf, verbose=10)
gs_clf = gs_clf.fit(df_train, df_train["rating"])

n_iterations: 3
n_required_iterations: 3
n_possible_iterations: 3
min_resources_: 875
max_resources_: 7881
aggressive_elimination: False
factor: 3
----------
iter: 0
n_candidates: 12
n_resources: 875
Fitting 5 folds for each of 12 candidates, totalling 60 fits
[CV 1/5; 1/12] START classifier__max_depth=None, classifier__n_estimators=50....
[CV 1/5; 1/12] END classifier__max_depth=None, classifier__n_estimators=50;, score=(train=1.000, test=0.331) total time=   0.3s
[CV 2/5; 1/12] START classifier__max_depth=None, classifier__n_estimators=50....
[CV 2/5; 1/12] END classifier__max_depth=None, classifier__n_estimators=50;, score=(train=1.000, test=0.293) total time=   0.4s
[CV 3/5; 1/12] START classifier__max_depth=None, classifier__n_estimators=50....
[CV 3/5; 1/12] END classifier__max_depth=None, classifier__n_estimators=50;, score=(train=1.000, test=0.287) total time=   0.4s
[CV 4/5; 1/12] START classifier__max_depth=None, classifier__n_estimators=50....
[CV 4/5; 1/12] END classifier__max_depth=None, classifier__n_estimators=50;, score=(train=1.000, test=0.270) total time=   0.4s
[CV 5/5; 1/12] START classifier__max_depth=None, classifier__n_estimators=50....
[CV 5/5; 1/12] END classifier__max_depth=None, classifier__n_estimators=50;, score=(train=1.000, test=0.236) total time=   0.3s
[CV 1/5; 2/12] START classifier__max_depth=None, classifier__n_estimators=100...
[CV 1/5; 2/12] END classifier__max_depth=None, classifier__n_estimators=100;, score=(train=1.000, test=0.360) total time=   0.5s
[CV 2/5; 2/12] START classifier__max_depth=None, classifier__n_estimators=100...
[CV 2/5; 2/12] END classifier__max_depth=None, classifier__n_estimators=100;, score=(train=1.000, test=0.287) total time=   0.5s
[CV 3/5; 2/12] START classifier__max_depth=None, classifier__n_estimators=100...
[CV 3/5; 2/12] END classifier__max_depth=None, classifier__n_estimators=100;, score=(train=1.000, test=0.293) total time=   0.5s
[CV 4/5; 2/12] START classifier__max_depth=None, classifier__n_estimators=100...
[CV 4/5; 2/12] END classifier__max_depth=None, classifier__n_estimators=100;, score=(train=1.000, test=0.259) total time=   0.5s
[CV 5/5; 2/12] START classifier__max_depth=None, classifier__n_estimators=100...
[CV 5/5; 2/12] END classifier__max_depth=None, classifier__n_estimators=100;, score=(train=1.000, test=0.259) total time=   0.5s
[CV 1/5; 3/12] START classifier__max_depth=None, classifier__n_estimators=200...
[CV 1/5; 3/12] END classifier__max_depth=None, classifier__n_estimators=200;, score=(train=1.000, test=0.320) total time=   0.9s
[CV 2/5; 3/12] START classifier__max_depth=None, classifier__n_estimators=200...
[CV 2/5; 3/12] END classifier__max_depth=None, classifier__n_estimators=200;, score=(train=1.000, test=0.339) total time=   1.0s
[CV 3/5; 3/12] START classifier__max_depth=None, classifier__n_estimators=200...
[CV 3/5; 3/12] END classifier__max_depth=None, classifier__n_estimators=200;, score=(train=1.000, test=0.328) total time=   0.9s
[CV 4/5; 3/12] START classifier__max_depth=None, classifier__n_estimators=200...
[CV 4/5; 3/12] END classifier__max_depth=None, classifier__n_estimators=200;, score=(train=1.000, test=0.270) total time=   1.0s
[CV 5/5; 3/12] START classifier__max_depth=None, classifier__n_estimators=200...
[CV 5/5; 3/12] END classifier__max_depth=None, classifier__n_estimators=200;, score=(train=1.000, test=0.299) total time=   0.9s
[CV 1/5; 4/12] START classifier__max_depth=50, classifier__n_estimators=50......
[CV 1/5; 4/12] END classifier__max_depth=50, classifier__n_estimators=50;, score=(train=1.000, test=0.331) total time=   0.3s
[CV 2/5; 4/12] START classifier__max_depth=50, classifier__n_estimators=50......
[CV 2/5; 4/12] END classifier__max_depth=50, classifier__n_estimators=50;, score=(train=1.000, test=0.299) total time=   0.3s
[CV 3/5; 4/12] START classifier__max_depth=50, classifier__n_estimators=50......
[CV 3/5; 4/12] END classifier__max_depth=50, classifier__n_estimators=50;, score=(train=1.000, test=0.310) total time=   0.3s
[CV 4/5; 4/12] START classifier__max_depth=50, classifier__n_estimators=50......
[CV 4/5; 4/12] END classifier__max_depth=50, classifier__n_estimators=50;, score=(train=1.000, test=0.287) total time=   0.4s
[CV 5/5; 4/12] START classifier__max_depth=50, classifier__n_estimators=50......
[CV 5/5; 4/12] END classifier__max_depth=50, classifier__n_estimators=50;, score=(train=1.000, test=0.287) total time=   0.4s
[CV 1/5; 5/12] START classifier__max_depth=50, classifier__n_estimators=100.....
[CV 1/5; 5/12] END classifier__max_depth=50, classifier__n_estimators=100;, score=(train=1.000, test=0.303) total time=   0.5s
[CV 2/5; 5/12] START classifier__max_depth=50, classifier__n_estimators=100.....
[CV 2/5; 5/12] END classifier__max_depth=50, classifier__n_estimators=100;, score=(train=1.000, test=0.322) total time=   0.6s
[CV 3/5; 5/12] START classifier__max_depth=50, classifier__n_estimators=100.....
[CV 3/5; 5/12] END classifier__max_depth=50, classifier__n_estimators=100;, score=(train=1.000, test=0.368) total time=   0.6s
[CV 4/5; 5/12] START classifier__max_depth=50, classifier__n_estimators=100.....
[CV 4/5; 5/12] END classifier__max_depth=50, classifier__n_estimators=100;, score=(train=1.000, test=0.316) total time=   0.6s
[CV 5/5; 5/12] START classifier__max_depth=50, classifier__n_estimators=100.....
[CV 5/5; 5/12] END classifier__max_depth=50, classifier__n_estimators=100;, score=(train=1.000, test=0.368) total time=   0.6s
[CV 1/5; 6/12] START classifier__max_depth=50, classifier__n_estimators=200.....
[CV 1/5; 6/12] END classifier__max_depth=50, classifier__n_estimators=200;, score=(train=1.000, test=0.309) total time=   1.0s
[CV 2/5; 6/12] START classifier__max_depth=50, classifier__n_estimators=200.....
[CV 2/5; 6/12] END classifier__max_depth=50, classifier__n_estimators=200;, score=(train=1.000, test=0.351) total time=   0.9s
[CV 3/5; 6/12] START classifier__max_depth=50, classifier__n_estimators=200.....
[CV 3/5; 6/12] END classifier__max_depth=50, classifier__n_estimators=200;, score=(train=1.000, test=0.333) total time=   0.9s
[CV 4/5; 6/12] START classifier__max_depth=50, classifier__n_estimators=200.....
[CV 4/5; 6/12] END classifier__max_depth=50, classifier__n_estimators=200;, score=(train=1.000, test=0.270) total time=   0.9s
[CV 5/5; 6/12] START classifier__max_depth=50, classifier__n_estimators=200.....
[CV 5/5; 6/12] END classifier__max_depth=50, classifier__n_estimators=200;, score=(train=1.000, test=0.328) total time=   0.8s
[CV 1/5; 7/12] START classifier__max_depth=100, classifier__n_estimators=50.....
[CV 1/5; 7/12] END classifier__max_depth=100, classifier__n_estimators=50;, score=(train=1.000, test=0.269) total time=   0.3s
[CV 2/5; 7/12] START classifier__max_depth=100, classifier__n_estimators=50.....
[CV 2/5; 7/12] END classifier__max_depth=100, classifier__n_estimators=50;, score=(train=1.000, test=0.316) total time=   0.3s
[CV 3/5; 7/12] START classifier__max_depth=100, classifier__n_estimators=50.....
[CV 3/5; 7/12] END classifier__max_depth=100, classifier__n_estimators=50;, score=(train=1.000, test=0.305) total time=   0.3s
[CV 4/5; 7/12] START classifier__max_depth=100, classifier__n_estimators=50.....
[CV 4/5; 7/12] END classifier__max_depth=100, classifier__n_estimators=50;, score=(train=1.000, test=0.236) total time=   0.4s
[CV 5/5; 7/12] START classifier__max_depth=100, classifier__n_estimators=50.....
[CV 5/5; 7/12] END classifier__max_depth=100, classifier__n_estimators=50;, score=(train=1.000, test=0.328) total time=   0.3s
[CV 1/5; 8/12] START classifier__max_depth=100, classifier__n_estimators=100....
[CV 1/5; 8/12] END classifier__max_depth=100, classifier__n_estimators=100;, score=(train=1.000, test=0.309) total time=   0.5s
[CV 2/5; 8/12] START classifier__max_depth=100, classifier__n_estimators=100....
[CV 2/5; 8/12] END classifier__max_depth=100, classifier__n_estimators=100;, score=(train=1.000, test=0.339) total time=   0.5s
[CV 3/5; 8/12] START classifier__max_depth=100, classifier__n_estimators=100....
[CV 3/5; 8/12] END classifier__max_depth=100, classifier__n_estimators=100;, score=(train=1.000, test=0.305) total time=   0.5s
[CV 4/5; 8/12] START classifier__max_depth=100, classifier__n_estimators=100....
[CV 4/5; 8/12] END classifier__max_depth=100, classifier__n_estimators=100;, score=(train=1.000, test=0.299) total time=   0.5s
[CV 5/5; 8/12] START classifier__max_depth=100, classifier__n_estimators=100....
[CV 5/5; 8/12] END classifier__max_depth=100, classifier__n_estimators=100;, score=(train=1.000, test=0.287) total time=   0.5s
[CV 1/5; 9/12] START classifier__max_depth=100, classifier__n_estimators=200....
[CV 1/5; 9/12] END classifier__max_depth=100, classifier__n_estimators=200;, score=(train=1.000, test=0.320) total time=   0.9s
[CV 2/5; 9/12] START classifier__max_depth=100, classifier__n_estimators=200....
[CV 2/5; 9/12] END classifier__max_depth=100, classifier__n_estimators=200;, score=(train=1.000, test=0.339) total time=   0.9s
[CV 3/5; 9/12] START classifier__max_depth=100, classifier__n_estimators=200....
[CV 3/5; 9/12] END classifier__max_depth=100, classifier__n_estimators=200;, score=(train=1.000, test=0.345) total time=   1.0s
[CV 4/5; 9/12] START classifier__max_depth=100, classifier__n_estimators=200....
[CV 4/5; 9/12] END classifier__max_depth=100, classifier__n_estimators=200;, score=(train=1.000, test=0.282) total time=   0.9s
[CV 5/5; 9/12] START classifier__max_depth=100, classifier__n_estimators=200....
[CV 5/5; 9/12] END classifier__max_depth=100, classifier__n_estimators=200;, score=(train=1.000, test=0.305) total time=   0.9s
[CV 1/5; 10/12] START classifier__max_depth=200, classifier__n_estimators=50....
[CV 1/5; 10/12] END classifier__max_depth=200, classifier__n_estimators=50;, score=(train=1.000, test=0.314) total time=   0.3s
[CV 2/5; 10/12] START classifier__max_depth=200, classifier__n_estimators=50....
[CV 2/5; 10/12] END classifier__max_depth=200, classifier__n_estimators=50;, score=(train=1.000, test=0.333) total time=   0.3s
[CV 3/5; 10/12] START classifier__max_depth=200, classifier__n_estimators=50....
[CV 3/5; 10/12] END classifier__max_depth=200, classifier__n_estimators=50;, score=(train=1.000, test=0.293) total time=   0.3s
[CV 4/5; 10/12] START classifier__max_depth=200, classifier__n_estimators=50....
[CV 4/5; 10/12] END classifier__max_depth=200, classifier__n_estimators=50;, score=(train=1.000, test=0.276) total time=   0.3s
[CV 5/5; 10/12] START classifier__max_depth=200, classifier__n_estimators=50....
[CV 5/5; 10/12] END classifier__max_depth=200, classifier__n_estimators=50;, score=(train=1.000, test=0.270) total time=   0.3s
[CV 1/5; 11/12] START classifier__max_depth=200, classifier__n_estimators=100...
[CV 1/5; 11/12] END classifier__max_depth=200, classifier__n_estimators=100;, score=(train=1.000, test=0.371) total time=   0.5s
[CV 2/5; 11/12] START classifier__max_depth=200, classifier__n_estimators=100...
[CV 2/5; 11/12] END classifier__max_depth=200, classifier__n_estimators=100;, score=(train=1.000, test=0.345) total time=   0.6s
[CV 3/5; 11/12] START classifier__max_depth=200, classifier__n_estimators=100...
[CV 3/5; 11/12] END classifier__max_depth=200, classifier__n_estimators=100;, score=(train=1.000, test=0.310) total time=   0.5s
[CV 4/5; 11/12] START classifier__max_depth=200, classifier__n_estimators=100...
[CV 4/5; 11/12] END classifier__max_depth=200, classifier__n_estimators=100;, score=(train=1.000, test=0.310) total time=   0.6s
[CV 5/5; 11/12] START classifier__max_depth=200, classifier__n_estimators=100...
[CV 5/5; 11/12] END classifier__max_depth=200, classifier__n_estimators=100;, score=(train=1.000, test=0.305) total time=   0.6s
[CV 1/5; 12/12] START classifier__max_depth=200, classifier__n_estimators=200...
[CV 1/5; 12/12] END classifier__max_depth=200, classifier__n_estimators=200;, score=(train=1.000, test=0.331) total time=   0.9s
[CV 2/5; 12/12] START classifier__max_depth=200, classifier__n_estimators=200...
[CV 2/5; 12/12] END classifier__max_depth=200, classifier__n_estimators=200;, score=(train=1.000, test=0.351) total time=   1.0s
[CV 3/5; 12/12] START classifier__max_depth=200, classifier__n_estimators=200...
[CV 3/5; 12/12] END classifier__max_depth=200, classifier__n_estimators=200;, score=(train=1.000, test=0.316) total time=   0.8s
[CV 4/5; 12/12] START classifier__max_depth=200, classifier__n_estimators=200...
[CV 4/5; 12/12] END classifier__max_depth=200, classifier__n_estimators=200;, score=(train=1.000, test=0.310) total time=   0.9s
[CV 5/5; 12/12] START classifier__max_depth=200, classifier__n_estimators=200...
[CV 5/5; 12/12] END classifier__max_depth=200, classifier__n_estimators=200;, score=(train=1.000, test=0.305) total time=   0.9s
----------
iter: 1
n_candidates: 4
n_resources: 2625
Fitting 5 folds for each of 4 candidates, totalling 20 fits
[CV 1/5; 1/4] START classifier__max_depth=50, classifier__n_estimators=200......
[CV 1/5; 1/4] END classifier__max_depth=50, classifier__n_estimators=200;, score=(train=1.000, test=0.307) total time=   4.4s
[CV 2/5; 1/4] START classifier__max_depth=50, classifier__n_estimators=200......
[CV 2/5; 1/4] END classifier__max_depth=50, classifier__n_estimators=200;, score=(train=1.000, test=0.319) total time=   4.2s
[CV 3/5; 1/4] START classifier__max_depth=50, classifier__n_estimators=200......
[CV 3/5; 1/4] END classifier__max_depth=50, classifier__n_estimators=200;, score=(train=1.000, test=0.288) total time=   4.2s
[CV 4/5; 1/4] START classifier__max_depth=50, classifier__n_estimators=200......
[CV 4/5; 1/4] END classifier__max_depth=50, classifier__n_estimators=200;, score=(train=1.000, test=0.326) total time=   4.3s
[CV 5/5; 1/4] START classifier__max_depth=50, classifier__n_estimators=200......
[CV 5/5; 1/4] END classifier__max_depth=50, classifier__n_estimators=200;, score=(train=1.000, test=0.277) total time=   4.2s
[CV 1/5; 2/4] START classifier__max_depth=200, classifier__n_estimators=200.....
[CV 1/5; 2/4] END classifier__max_depth=200, classifier__n_estimators=200;, score=(train=1.000, test=0.314) total time=   5.0s
[CV 2/5; 2/4] START classifier__max_depth=200, classifier__n_estimators=200.....
[CV 2/5; 2/4] END classifier__max_depth=200, classifier__n_estimators=200;, score=(train=1.000, test=0.345) total time=   4.8s
[CV 3/5; 2/4] START classifier__max_depth=200, classifier__n_estimators=200.....
[CV 3/5; 2/4] END classifier__max_depth=200, classifier__n_estimators=200;, score=(train=1.000, test=0.281) total time=   4.7s
[CV 4/5; 2/4] START classifier__max_depth=200, classifier__n_estimators=200.....
[CV 4/5; 2/4] END classifier__max_depth=200, classifier__n_estimators=200;, score=(train=1.000, test=0.305) total time=   4.9s
[CV 5/5; 2/4] START classifier__max_depth=200, classifier__n_estimators=200.....
[CV 5/5; 2/4] END classifier__max_depth=200, classifier__n_estimators=200;, score=(train=1.000, test=0.303) total time=   4.9s
[CV 1/5; 3/4] START classifier__max_depth=200, classifier__n_estimators=100.....
[CV 1/5; 3/4] END classifier__max_depth=200, classifier__n_estimators=100;, score=(train=1.000, test=0.291) total time=   2.6s
[CV 2/5; 3/4] START classifier__max_depth=200, classifier__n_estimators=100.....
[CV 2/5; 3/4] END classifier__max_depth=200, classifier__n_estimators=100;, score=(train=1.000, test=0.334) total time=   2.6s
[CV 3/5; 3/4] START classifier__max_depth=200, classifier__n_estimators=100.....
[CV 3/5; 3/4] END classifier__max_depth=200, classifier__n_estimators=100;, score=(train=1.000, test=0.275) total time=   2.5s
[CV 4/5; 3/4] START classifier__max_depth=200, classifier__n_estimators=100.....
[CV 4/5; 3/4] END classifier__max_depth=200, classifier__n_estimators=100;, score=(train=1.000, test=0.330) total time=   2.7s
[CV 5/5; 3/4] START classifier__max_depth=200, classifier__n_estimators=100.....
[CV 5/5; 3/4] END classifier__max_depth=200, classifier__n_estimators=100;, score=(train=1.000, test=0.321) total time=   2.6s
[CV 1/5; 4/4] START classifier__max_depth=50, classifier__n_estimators=100......
[CV 1/5; 4/4] END classifier__max_depth=50, classifier__n_estimators=100;, score=(train=0.999, test=0.312) total time=   2.3s
[CV 2/5; 4/4] START classifier__max_depth=50, classifier__n_estimators=100......
[CV 2/5; 4/4] END classifier__max_depth=50, classifier__n_estimators=100;, score=(train=0.999, test=0.296) total time=   2.4s
[CV 3/5; 4/4] START classifier__max_depth=50, classifier__n_estimators=100......
[CV 3/5; 4/4] END classifier__max_depth=50, classifier__n_estimators=100;, score=(train=1.000, test=0.315) total time=   2.2s
[CV 4/5; 4/4] START classifier__max_depth=50, classifier__n_estimators=100......
[CV 4/5; 4/4] END classifier__max_depth=50, classifier__n_estimators=100;, score=(train=1.000, test=0.309) total time=   2.2s
[CV 5/5; 4/4] START classifier__max_depth=50, classifier__n_estimators=100......
[CV 5/5; 4/4] END classifier__max_depth=50, classifier__n_estimators=100;, score=(train=0.999, test=0.277) total time=   2.3s
----------
iter: 2
n_candidates: 2
n_resources: 7875
Fitting 5 folds for each of 2 candidates, totalling 10 fits
[CV 1/5; 1/2] START classifier__max_depth=200, classifier__n_estimators=200.....
[CV 1/5; 1/2] END classifier__max_depth=200, classifier__n_estimators=200;, score=(train=0.999, test=0.356) total time=  36.0s
[CV 2/5; 1/2] START classifier__max_depth=200, classifier__n_estimators=200.....
[CV 2/5; 1/2] END classifier__max_depth=200, classifier__n_estimators=200;, score=(train=0.999, test=0.358) total time=  35.0s
[CV 3/5; 1/2] START classifier__max_depth=200, classifier__n_estimators=200.....
[CV 3/5; 1/2] END classifier__max_depth=200, classifier__n_estimators=200;, score=(train=0.999, test=0.360) total time=  33.8s
[CV 4/5; 1/2] START classifier__max_depth=200, classifier__n_estimators=200.....
[CV 4/5; 1/2] END classifier__max_depth=200, classifier__n_estimators=200;, score=(train=0.999, test=0.356) total time=  35.8s
[CV 5/5; 1/2] START classifier__max_depth=200, classifier__n_estimators=200.....
[CV 5/5; 1/2] END classifier__max_depth=200, classifier__n_estimators=200;, score=(train=0.999, test=0.341) total time=  34.7s
[CV 1/5; 2/2] START classifier__max_depth=200, classifier__n_estimators=100.....
[CV 1/5; 2/2] END classifier__max_depth=200, classifier__n_estimators=100;, score=(train=0.999, test=0.334) total time=  20.3s
[CV 2/5; 2/2] START classifier__max_depth=200, classifier__n_estimators=100.....
[CV 2/5; 2/2] END classifier__max_depth=200, classifier__n_estimators=100;, score=(train=0.999, test=0.336) total time=  19.2s
[CV 3/5; 2/2] START classifier__max_depth=200, classifier__n_estimators=100.....
[CV 3/5; 2/2] END classifier__max_depth=200, classifier__n_estimators=100;, score=(train=0.999, test=0.357) total time=  20.1s
[CV 4/5; 2/2] START classifier__max_depth=200, classifier__n_estimators=100.....
[CV 4/5; 2/2] END classifier__max_depth=200, classifier__n_estimators=100;, score=(train=0.999, test=0.341) total time=  20.1s
[CV 5/5; 2/2] START classifier__max_depth=200, classifier__n_estimators=100.....
[CV 5/5; 2/2] END classifier__max_depth=200, classifier__n_estimators=100;, score=(train=0.999, test=0.333) total time=  26.6s


param_grid_reg = {'regressor__max_depth': [3,4,5], 'regressor__n_estimators': [50,100,200]}

gs_reg = HalvingGridSearchCV(clf_regressor, param_grid_reg, verbose=10)
gs_reg = gs_reg.fit(df_train, df_train["estimated_sells"])

n_iterations: 3
n_required_iterations: 3
n_possible_iterations: 3
min_resources_: 875
max_resources_: 7881
aggressive_elimination: False
factor: 3
----------
iter: 0
n_candidates: 9
n_resources: 875
Fitting 5 folds for each of 9 candidates, totalling 45 fits
[CV 1/5; 1/9] START regressor__max_depth=3, regressor__n_estimators=50..........
[CV 1/5; 1/9] END regressor__max_depth=3, regressor__n_estimators=50;, score=(train=0.996, test=0.322) total time=   0.8s
[CV 2/5; 1/9] START regressor__max_depth=3, regressor__n_estimators=50..........
[CV 2/5; 1/9] END regressor__max_depth=3, regressor__n_estimators=50;, score=(train=0.991, test=-4.001) total time=   0.7s
[CV 3/5; 1/9] START regressor__max_depth=3, regressor__n_estimators=50..........
[CV 3/5; 1/9] END regressor__max_depth=3, regressor__n_estimators=50;, score=(train=0.996, test=0.418) total time=   0.8s
[CV 4/5; 1/9] START regressor__max_depth=3, regressor__n_estimators=50..........
[CV 4/5; 1/9] END regressor__max_depth=3, regressor__n_estimators=50;, score=(train=0.977, test=0.381) total time=   0.8s
[CV 5/5; 1/9] START regressor__max_depth=3, regressor__n_estimators=50..........
[CV 5/5; 1/9] END regressor__max_depth=3, regressor__n_estimators=50;, score=(train=0.937, test=0.021) total time=   0.8s
[CV 1/5; 2/9] START regressor__max_depth=3, regressor__n_estimators=100.........
[CV 1/5; 2/9] END regressor__max_depth=3, regressor__n_estimators=100;, score=(train=0.998, test=0.326) total time=   1.5s
[CV 2/5; 2/9] START regressor__max_depth=3, regressor__n_estimators=100.........
[CV 2/5; 2/9] END regressor__max_depth=3, regressor__n_estimators=100;, score=(train=0.997, test=-4.084) total time=   4.0s
[CV 3/5; 2/9] START regressor__max_depth=3, regressor__n_estimators=100.........
[CV 3/5; 2/9] END regressor__max_depth=3, regressor__n_estimators=100;, score=(train=0.998, test=0.417) total time=   1.5s
[CV 4/5; 2/9] START regressor__max_depth=3, regressor__n_estimators=100.........
[CV 4/5; 2/9] END regressor__max_depth=3, regressor__n_estimators=100;, score=(train=0.991, test=0.380) total time=   1.4s
[CV 5/5; 2/9] START regressor__max_depth=3, regressor__n_estimators=100.........
[CV 5/5; 2/9] END regressor__max_depth=3, regressor__n_estimators=100;, score=(train=0.971, test=0.019) total time=   1.5s
[CV 1/5; 3/9] START regressor__max_depth=3, regressor__n_estimators=200.........
[CV 1/5; 3/9] END regressor__max_depth=3, regressor__n_estimators=200;, score=(train=1.000, test=0.327) total time=   3.9s
[CV 2/5; 3/9] START regressor__max_depth=3, regressor__n_estimators=200.........
[CV 2/5; 3/9] END regressor__max_depth=3, regressor__n_estimators=200;, score=(train=0.999, test=-4.109) total time=   3.2s
[CV 3/5; 3/9] START regressor__max_depth=3, regressor__n_estimators=200.........
[CV 3/5; 3/9] END regressor__max_depth=3, regressor__n_estimators=200;, score=(train=0.999, test=0.415) total time=   3.2s
[CV 4/5; 3/9] START regressor__max_depth=3, regressor__n_estimators=200.........
[CV 4/5; 3/9] END regressor__max_depth=3, regressor__n_estimators=200;, score=(train=0.997, test=0.385) total time=   3.2s
[CV 5/5; 3/9] START regressor__max_depth=3, regressor__n_estimators=200.........
[CV 5/5; 3/9] END regressor__max_depth=3, regressor__n_estimators=200;, score=(train=0.990, test=0.019) total time=   3.2s
[CV 1/5; 4/9] START regressor__max_depth=4, regressor__n_estimators=50..........
[CV 1/5; 4/9] END regressor__max_depth=4, regressor__n_estimators=50;, score=(train=0.998, test=0.291) total time=   0.9s
[CV 2/5; 4/9] START regressor__max_depth=4, regressor__n_estimators=50..........
[CV 2/5; 4/9] END regressor__max_depth=4, regressor__n_estimators=50;, score=(train=0.996, test=-4.012) total time=   1.1s
[CV 3/5; 4/9] START regressor__max_depth=4, regressor__n_estimators=50..........
[CV 3/5; 4/9] END regressor__max_depth=4, regressor__n_estimators=50;, score=(train=0.998, test=0.433) total time=   1.0s
[CV 4/5; 4/9] START regressor__max_depth=4, regressor__n_estimators=50..........
[CV 4/5; 4/9] END regressor__max_depth=4, regressor__n_estimators=50;, score=(train=0.989, test=0.320) total time=   1.0s
[CV 5/5; 4/9] START regressor__max_depth=4, regressor__n_estimators=50..........
[CV 5/5; 4/9] END regressor__max_depth=4, regressor__n_estimators=50;, score=(train=0.971, test=0.016) total time=   0.9s
[CV 1/5; 5/9] START regressor__max_depth=4, regressor__n_estimators=100.........
[CV 1/5; 5/9] END regressor__max_depth=4, regressor__n_estimators=100;, score=(train=0.999, test=0.292) total time=   1.6s
[CV 2/5; 5/9] START regressor__max_depth=4, regressor__n_estimators=100.........
[CV 2/5; 5/9] END regressor__max_depth=4, regressor__n_estimators=100;, score=(train=0.999, test=-4.062) total time=   1.7s
[CV 3/5; 5/9] START regressor__max_depth=4, regressor__n_estimators=100.........
[CV 3/5; 5/9] END regressor__max_depth=4, regressor__n_estimators=100;, score=(train=0.999, test=0.435) total time=   1.6s
[CV 4/5; 5/9] START regressor__max_depth=4, regressor__n_estimators=100.........
[CV 4/5; 5/9] END regressor__max_depth=4, regressor__n_estimators=100;, score=(train=0.996, test=0.330) total time=   1.7s
[CV 5/5; 5/9] START regressor__max_depth=4, regressor__n_estimators=100.........
[CV 5/5; 5/9] END regressor__max_depth=4, regressor__n_estimators=100;, score=(train=0.987, test=0.015) total time=   1.7s
[CV 1/5; 6/9] START regressor__max_depth=4, regressor__n_estimators=200.........
[CV 1/5; 6/9] END regressor__max_depth=4, regressor__n_estimators=200;, score=(train=1.000, test=0.292) total time=   3.2s
[CV 2/5; 6/9] START regressor__max_depth=4, regressor__n_estimators=200.........
[CV 2/5; 6/9] END regressor__max_depth=4, regressor__n_estimators=200;, score=(train=1.000, test=-4.074) total time=   3.3s
[CV 3/5; 6/9] START regressor__max_depth=4, regressor__n_estimators=200.........
[CV 3/5; 6/9] END regressor__max_depth=4, regressor__n_estimators=200;, score=(train=1.000, test=0.435) total time=   3.0s
[CV 4/5; 6/9] START regressor__max_depth=4, regressor__n_estimators=200.........
[CV 4/5; 6/9] END regressor__max_depth=4, regressor__n_estimators=200;, score=(train=0.999, test=0.342) total time=   6.3s
[CV 5/5; 6/9] START regressor__max_depth=4, regressor__n_estimators=200.........
[CV 5/5; 6/9] END regressor__max_depth=4, regressor__n_estimators=200;, score=(train=0.996, test=0.017) total time=   4.4s
[CV 1/5; 7/9] START regressor__max_depth=5, regressor__n_estimators=50..........
[CV 1/5; 7/9] END regressor__max_depth=5, regressor__n_estimators=50;, score=(train=0.999, test=0.263) total time=   1.2s
[CV 2/5; 7/9] START regressor__max_depth=5, regressor__n_estimators=50..........
[CV 2/5; 7/9] END regressor__max_depth=5, regressor__n_estimators=50;, score=(train=0.998, test=-3.987) total time=   1.2s
[CV 3/5; 7/9] START regressor__max_depth=5, regressor__n_estimators=50..........
[CV 3/5; 7/9] END regressor__max_depth=5, regressor__n_estimators=50;, score=(train=0.999, test=0.437) total time=   1.9s
[CV 4/5; 7/9] START regressor__max_depth=5, regressor__n_estimators=50..........
[CV 4/5; 7/9] END regressor__max_depth=5, regressor__n_estimators=50;, score=(train=0.994, test=0.346) total time=   4.0s
[CV 5/5; 7/9] START regressor__max_depth=5, regressor__n_estimators=50..........
[CV 5/5; 7/9] END regressor__max_depth=5, regressor__n_estimators=50;, score=(train=0.980, test=0.024) total time=   1.4s
[CV 1/5; 8/9] START regressor__max_depth=5, regressor__n_estimators=100.........
[CV 1/5; 8/9] END regressor__max_depth=5, regressor__n_estimators=100;, score=(train=1.000, test=0.265) total time=   2.9s
[CV 2/5; 8/9] START regressor__max_depth=5, regressor__n_estimators=100.........
[CV 2/5; 8/9] END regressor__max_depth=5, regressor__n_estimators=100;, score=(train=0.999, test=-4.010) total time=   4.1s
[CV 3/5; 8/9] START regressor__max_depth=5, regressor__n_estimators=100.........
[CV 3/5; 8/9] END regressor__max_depth=5, regressor__n_estimators=100;, score=(train=1.000, test=0.437) total time=   7.9s
[CV 4/5; 8/9] START regressor__max_depth=5, regressor__n_estimators=100.........
[CV 4/5; 8/9] END regressor__max_depth=5, regressor__n_estimators=100;, score=(train=0.998, test=0.360) total time=   2.8s
[CV 5/5; 8/9] START regressor__max_depth=5, regressor__n_estimators=100.........
[CV 5/5; 8/9] END regressor__max_depth=5, regressor__n_estimators=100;, score=(train=0.993, test=0.027) total time=   3.6s
[CV 1/5; 9/9] START regressor__max_depth=5, regressor__n_estimators=200.........
[CV 1/5; 9/9] END regressor__max_depth=5, regressor__n_estimators=200;, score=(train=1.000, test=0.266) total time=   8.7s
[CV 2/5; 9/9] START regressor__max_depth=5, regressor__n_estimators=200.........
[CV 2/5; 9/9] END regressor__max_depth=5, regressor__n_estimators=200;, score=(train=1.000, test=-4.012) total time=   3.2s
[CV 3/5; 9/9] START regressor__max_depth=5, regressor__n_estimators=200.........
[CV 3/5; 9/9] END regressor__max_depth=5, regressor__n_estimators=200;, score=(train=1.000, test=0.437) total time=   3.1s
[CV 4/5; 9/9] START regressor__max_depth=5, regressor__n_estimators=200.........
[CV 4/5; 9/9] END regressor__max_depth=5, regressor__n_estimators=200;, score=(train=0.999, test=0.365) total time=   3.3s
[CV 5/5; 9/9] START regressor__max_depth=5, regressor__n_estimators=200.........
[CV 5/5; 9/9] END regressor__max_depth=5, regressor__n_estimators=200;, score=(train=0.998, test=0.028) total time=   3.5s
----------
iter: 1
n_candidates: 3
n_resources: 2625
Fitting 5 folds for each of 3 candidates, totalling 15 fits
[CV 1/5; 1/3] START regressor__max_depth=5, regressor__n_estimators=50..........
[CV 1/5; 1/3] END regressor__max_depth=5, regressor__n_estimators=50;, score=(train=0.982, test=0.108) total time=   5.0s
[CV 2/5; 1/3] START regressor__max_depth=5, regressor__n_estimators=50..........
[CV 2/5; 1/3] END regressor__max_depth=5, regressor__n_estimators=50;, score=(train=0.946, test=0.192) total time=   4.9s
[CV 3/5; 1/3] START regressor__max_depth=5, regressor__n_estimators=50..........
[CV 3/5; 1/3] END regressor__max_depth=5, regressor__n_estimators=50;, score=(train=0.984, test=0.063) total time=   4.5s
[CV 4/5; 1/3] START regressor__max_depth=5, regressor__n_estimators=50..........
[CV 4/5; 1/3] END regressor__max_depth=5, regressor__n_estimators=50;, score=(train=0.997, test=0.509) total time=   4.9s
[CV 5/5; 1/3] START regressor__max_depth=5, regressor__n_estimators=50..........
[CV 5/5; 1/3] END regressor__max_depth=5, regressor__n_estimators=50;, score=(train=0.982, test=0.219) total time=   4.9s
[CV 1/5; 2/3] START regressor__max_depth=5, regressor__n_estimators=200.........
[CV 1/5; 2/3] END regressor__max_depth=5, regressor__n_estimators=200;, score=(train=0.996, test=0.115) total time=  21.1s
[CV 2/5; 2/3] START regressor__max_depth=5, regressor__n_estimators=200.........
[CV 2/5; 2/3] END regressor__max_depth=5, regressor__n_estimators=200;, score=(train=0.992, test=0.199) total time=  19.6s
[CV 3/5; 2/3] START regressor__max_depth=5, regressor__n_estimators=200.........
[CV 3/5; 2/3] END regressor__max_depth=5, regressor__n_estimators=200;, score=(train=0.998, test=0.087) total time=  20.2s
[CV 4/5; 2/3] START regressor__max_depth=5, regressor__n_estimators=200.........
[CV 4/5; 2/3] END regressor__max_depth=5, regressor__n_estimators=200;, score=(train=0.999, test=0.505) total time=  17.9s
[CV 5/5; 2/3] START regressor__max_depth=5, regressor__n_estimators=200.........
[CV 5/5; 2/3] END regressor__max_depth=5, regressor__n_estimators=200;, score=(train=0.997, test=0.159) total time=  17.9s
[CV 1/5; 3/3] START regressor__max_depth=3, regressor__n_estimators=50..........
[CV 1/5; 3/3] END regressor__max_depth=3, regressor__n_estimators=50;, score=(train=0.952, test=0.181) total time=   3.4s
[CV 2/5; 3/3] START regressor__max_depth=3, regressor__n_estimators=50..........
[CV 2/5; 3/3] END regressor__max_depth=3, regressor__n_estimators=50;, score=(train=0.871, test=0.161) total time=   3.6s
[CV 3/5; 3/3] START regressor__max_depth=3, regressor__n_estimators=50..........
[CV 3/5; 3/3] END regressor__max_depth=3, regressor__n_estimators=50;, score=(train=0.956, test=0.057) total time=   3.5s
[CV 4/5; 3/3] START regressor__max_depth=3, regressor__n_estimators=50..........
[CV 4/5; 3/3] END regressor__max_depth=3, regressor__n_estimators=50;, score=(train=0.984, test=0.437) total time=   3.1s
[CV 5/5; 3/3] START regressor__max_depth=3, regressor__n_estimators=50..........
[CV 5/5; 3/3] END regressor__max_depth=3, regressor__n_estimators=50;, score=(train=0.937, test=0.019) total time=   3.5s
----------
iter: 2
n_candidates: 1
n_resources: 7875
Fitting 5 folds for each of 1 candidates, totalling 5 fits
[CV 1/5; 1/1] START regressor__max_depth=5, regressor__n_estimators=50..........
[CV 1/5; 1/1] END regressor__max_depth=5, regressor__n_estimators=50;, score=(train=0.968, test=0.217) total time=  32.0s
[CV 2/5; 1/1] START regressor__max_depth=5, regressor__n_estimators=50..........
[CV 2/5; 1/1] END regressor__max_depth=5, regressor__n_estimators=50;, score=(train=0.963, test=-0.367) total time=  32.0s
[CV 3/5; 1/1] START regressor__max_depth=5, regressor__n_estimators=50..........
[CV 3/5; 1/1] END regressor__max_depth=5, regressor__n_estimators=50;, score=(train=0.952, test=0.170) total time=  33.3s
[CV 4/5; 1/1] START regressor__max_depth=5, regressor__n_estimators=50..........
[CV 4/5; 1/1] END regressor__max_depth=5, regressor__n_estimators=50;, score=(train=0.967, test=0.255) total time=  31.8s
[CV 5/5; 1/1] START regressor__max_depth=5, regressor__n_estimators=50..........
[CV 5/5; 1/1] END regressor__max_depth=5, regressor__n_estimators=50;, score=(train=0.967, test=-1.139) total time=  33.1s


from zipfile import ZipFile
import os

def generateFiles(predict_data, clf_pipe, rgr_pipe):
    """Genera los archivos a subir en CodaLab

    Input
    predict_data: Dataframe con los datos de entrada a predecir
    clf_pipe: pipeline del clf
    rgr_pipe: pipeline del rgr

    Ouput
    archivo de txt
    """
    y_pred_clf = clf_pipe.predict(predict_data)
    y_pred_rgr = rgr_pipe.predict(predict_data)
    
    with open('./predictions_clf.txt', 'w') as f:
        for item in y_pred_clf:
            f.write("%s\n" % item)

    with open('./predictions_rgr.txt', 'w') as f:
        for item in y_pred_rgr:
            f.write("%s\n" % item)

    with ZipFile('predictions.zip', 'w') as zipObj2:
       zipObj2.write('predictions_rgr.txt')
       zipObj2.write('predictions_clf.txt')

    os.remove("predictions_rgr.txt")
    os.remove("predictions_clf.txt")


generateFiles(df_test, gs_clf, gs_reg)

	name	release_date	english	developer	publisher	platforms	required_age	categories	genres	tags	achievements	average_playtime	price	short_description	estimated_sells	rating	rating_numeric
0	An Aspie Life	2018-03-29	1	Bradley Hennessey;Joe Watson	EnderLost Studios	windows	0	Single-player;Steam Achievements	Adventure;Casual;Free to Play;Indie;Simulation	Free to Play;Adventure;Indie	23	0	0.00	One day your roommate Leaves for no reason. Yo...	3914	Mixed	1.0
1	GhostControl Inc.	2014-06-06	1	bumblebee	Application Systems Heidelberg	windows;mac;linux	0	Single-player;Steam Achievements;Steam Trading...	Casual;Indie;Simulation;Strategy	Turn-Based;Indie;Simulation	53	65	10.99	Manage a team of ghosthunters and free London ...	10728	Mixed	1.0
2	Deponia	2012-08-06	1	Daedalic Entertainment	Daedalic Entertainment	windows;mac;linux	0	Single-player;Steam Achievements;Steam Trading...	Adventure;Indie	Adventure;Point & Click;Comedy	19	217	6.99	In Deponia, the world has degenerated into a v...	635792	Positive	3.0
3	Atlas Reactor	2016-10-04	1	Trion Worlds	Trion Worlds	windows	0	Multi-player;Online Multi-Player;Steam Achieve...	Free to Play;Strategy	Free to Play;Multiplayer;Strategy	121	1240	0.00	SEASON 6 NOW LIVE! The battle for Atlas contin...	253864	Positive	3.0
4	CHUCHEL	2018-03-07	1	Amanita Design	Amanita Design	windows;mac	0	Single-player;Steam Achievements;Steam Trading...	Adventure;Casual;Indie	Adventure;Indie;Casual	7	245	7.99	CHUCHEL is a comedy adventure game from the cr...	49818	Mostly Positive	2.0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
7876	KOEWOTAYORINI / 声之寄托	2018-03-26	0	あみそ組	Pujia8 Studio;Gamera Game	windows	0	Single-player;Steam Achievements;Steam Cloud	Adventure;Free to Play;Indie;RPG	Free to Play;Adventure;Anime	20	65	0.00	“喂喂，求求你啦！救救我！” ——你接到这样一个电话发出这样的求救，给你打电话的人，是一名...	24130	Positive	3.0
7877	Montaro	2016-07-25	1	JCKSLAP	MBDL	windows	0	Single-player;Steam Achievements;Steam Trading...	Casual;Indie	Memes;Cute;Casual	15	174	0.79	Montaro is a DOGE.	550368	Very Positive	4.0
7878	Moe Jigsaw	2018-03-23	1	ARES Inc.	ARES Inc.	windows	0	Single-player;Steam Achievements;Steam Trading...	Casual;Indie	Casual;Nudity;Indie	72	0	2.89	"Moe Jigsaw" is the definitive versi...	10906	Mostly Positive	2.0
7879	Drunkn Bar Fight	2016-11-28	1	The Munky	The Munky	windows	0	Single-player;Multi-player;Online Multi-Player...	Action;Indie;Early Access	Early Access;Action;Indie	0	0	10.99	VR PARTY GAMEDrunkn Bar Fight is a simple, imm...	18876	Mostly Positive	2.0
7880	Intake	2013-11-06	1	Cipher Prime Studios	Cipher Prime Studios	windows;mac	0	Single-player;Steam Achievements;Steam Cloud;S...	Action;Indie	Indie;Action;Great Soundtrack	77	75	6.99	Intake is the new retro-futuristic drugstep ar...	29625	Very Positive	4.0

	english	required_age	achievements	average_playtime	price	estimated_sells	rating_numeric
count	7881.000000	7881.00000	7881.000000	7881.000000	7881.000000	7.881000e+03	7881.000000
mean	0.985789	0.78924	43.170156	439.296790	8.431342	2.105767e+05	2.023982
std	0.118369	3.55538	265.399206	3303.162083	8.755668	1.513926e+06	1.315201
min	0.000000	0.00000	0.000000	0.000000	0.000000	3.600000e+03	0.000000
25%	1.000000	0.00000	0.000000	0.000000	1.990000	9.724000e+03	1.000000
50%	1.000000	0.00000	15.000000	27.000000	6.990000	2.150800e+04	2.000000
75%	1.000000	0.00000	35.000000	251.000000	11.390000	7.357300e+04	3.000000
max	1.000000	18.00000	9821.000000	190625.000000	78.990000	7.944129e+07	4.000000

	english	required_age	achievements	average_playtime	price	estimated_sells	rating_numeric
english	1.000000	0.015799	0.009748	-0.007678	0.018056	0.014292	-0.037753
required_age	0.015799	1.000000	-0.001500	0.026692	0.157875	0.110789	0.041111
achievements	0.009748	-0.001500	1.000000	0.000825	-0.026374	0.022180	-0.020295
average_playtime	-0.007678	0.026692	0.000825	1.000000	0.045651	0.161612	0.031250
price	0.018056	0.157875	-0.026374	0.045651	1.000000	0.062935	0.090508
estimated_sells	0.014292	0.110789	0.022180	0.161612	0.062935	1.000000	0.090395
rating_numeric	-0.037753	0.041111	-0.020295	0.031250	0.090508	0.090395	1.000000

	name	release_date	english	developer	publisher	platforms	required_age	categories	genres	tags	achievements	average_playtime	price	short_description	estimated_sells	rating	rating_numeric
0	An Aspie Life	2018-03-29	1	Bradley Hennessey;Joe Watson	EnderLost Studios	windows	0	Single-player;Steam Achievements	Adventure;Casual;Free to Play;Indie;Simulation	Free to Play;Adventure;Indie	23	0	0.00	One day your roommate Leaves for no reason. Yo...	3914	Mixed	1.0
1	GhostControl Inc.	2014-06-06	1	bumblebee	Application Systems Heidelberg	windows;mac;linux	0	Single-player;Steam Achievements;Steam Trading...	Casual;Indie;Simulation;Strategy	Turn-Based;Indie;Simulation	53	65	10.99	Manage a team of ghosthunters and free London ...	10728	Mixed	1.0
2	Deponia	2012-08-06	1	Daedalic Entertainment	Daedalic Entertainment	windows;mac;linux	0	Single-player;Steam Achievements;Steam Trading...	Adventure;Indie	Adventure;Point & Click;Comedy	19	217	6.99	In Deponia, the world has degenerated into a v...	635792	Positive	3.0
3	Atlas Reactor	2016-10-04	1	Trion Worlds	Trion Worlds	windows	0	Multi-player;Online Multi-Player;Steam Achieve...	Free to Play;Strategy	Free to Play;Multiplayer;Strategy	121	1240	0.00	SEASON 6 NOW LIVE! The battle for Atlas contin...	253864	Positive	3.0
4	CHUCHEL	2018-03-07	1	Amanita Design	Amanita Design	windows;mac	0	Single-player;Steam Achievements;Steam Trading...	Adventure;Casual;Indie	Adventure;Indie;Casual	7	245	7.99	CHUCHEL is a comedy adventure game from the cr...	49818	Mostly Positive	2.0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
7876	KOEWOTAYORINI / 声之寄托	2018-03-26	0	あみそ組	Pujia8 Studio;Gamera Game	windows	0	Single-player;Steam Achievements;Steam Cloud	Adventure;Free to Play;Indie;RPG	Free to Play;Adventure;Anime	20	65	0.00	“喂喂，求求你啦！救救我！” ——你接到这样一个电话发出这样的求救，给你打电话的人，是一名...	24130	Positive	3.0
7877	Montaro	2016-07-25	1	JCKSLAP	MBDL	windows	0	Single-player;Steam Achievements;Steam Trading...	Casual;Indie	Memes;Cute;Casual	15	174	0.79	Montaro is a DOGE.	550368	Very Positive	4.0
7878	Moe Jigsaw	2018-03-23	1	ARES Inc.	ARES Inc.	windows	0	Single-player;Steam Achievements;Steam Trading...	Casual;Indie	Casual;Nudity;Indie	72	0	2.89	"Moe Jigsaw" is the definitive versi...	10906	Mostly Positive	2.0
7879	Drunkn Bar Fight	2016-11-28	1	The Munky	The Munky	windows	0	Single-player;Multi-player;Online Multi-Player...	Action;Indie;Early Access	Early Access;Action;Indie	0	0	10.99	VR PARTY GAMEDrunkn Bar Fight is a simple, imm...	18876	Mostly Positive	2.0
7880	Intake	2013-11-06	1	Cipher Prime Studios	Cipher Prime Studios	windows;mac	0	Single-player;Steam Achievements;Steam Cloud;S...	Action;Indie	Indie;Action;Great Soundtrack	77	75	6.99	Intake is the new retro-futuristic drugstep ar...	29625	Very Positive	4.0

	english	required_age	achievements	average_playtime	price	estimated_sells	rating_numeric
count	7624.000000	7624.000000	7624.000000	7624.000000	7624.000000	7.624000e+03	7624.000000
mean	0.985703	0.699895	42.283447	194.372770	8.270792	8.968644e+04	1.998426
std	0.118720	3.346910	268.334142	408.893233	8.532924	1.998071e+05	1.310108
min	0.000000	0.000000	0.000000	0.000000	0.000000	3.600000e+03	0.000000
25%	1.000000	0.000000	0.000000	0.000000	1.990000	9.503750e+03	1.000000
50%	1.000000	0.000000	15.000000	18.000000	6.990000	2.024250e+04	2.000000
75%	1.000000	0.000000	34.000000	232.000000	11.390000	6.485700e+04	3.000000
max	1.000000	18.000000	9821.000000	3736.000000	78.990000	1.709876e+06	4.000000

Proyecto: El Desafío de Don Rene¶

Cuerpo Docente:¶

Proyecto¶

Equipo:¶

Link de repositorio de GitHub: `https://github.com/josebarross/laboratorio-programacion`¶

Imports¶

1. Introducción¶

2. Análisis Exploratorio de Datos¶

Describe¶

Correlations¶

Histogramas variables categóricas¶

Histogramas variables númericas mas relevantes¶

Histogramas variables númericas mas relevantes (Estimated sells)¶

Proyeccion 2-D¶

3. Preparación de Datos¶

4. Baseline¶

Results testing baseline - Rating¶

Results testing baseline - Estimted sells¶

5. Optimización del Modelo¶

6. Conclusiones¶

Anexo: Generación de Archivo Submit de la Competencia¶

	english	required_age	achievements	average_playtime	price	estimated_sells	rating_numeric
english	1.000000	0.013301	0.009920	0.006641	0.018885	0.037055	-0.042316
required_age	0.013301	1.000000	-0.007729	0.094450	0.143127	0.204879	0.026638
achievements	0.009920	-0.007729	1.000000	-0.000748	-0.029537	-0.000872	-0.023986
average_playtime	0.006641	0.094450	-0.000748	1.000000	0.228304	0.426791	0.080054
price	0.018885	0.143127	-0.029537	0.228304	1.000000	0.186764	0.087657
estimated_sells	0.037055	0.204879	-0.000872	0.426791	0.186764	1.000000	0.203393
rating_numeric	-0.042316	0.026638	-0.023986	0.080054	0.087657	0.203393	1.000000

Proyecto: El Desafío de Don Rene¶

Cuerpo Docente:¶

Proyecto¶

Equipo:¶

Link de repositorio de GitHub: https://github.com/josebarross/laboratorio-programacion¶

Imports¶

1. Introducción¶

2. Análisis Exploratorio de Datos¶

Describe¶

Correlations¶

Histogramas variables categóricas¶

Histogramas variables númericas mas relevantes¶

Histogramas variables númericas mas relevantes (Estimated sells)¶

Proyeccion 2-D¶

3. Preparación de Datos¶

4. Baseline¶

Results testing baseline - Rating¶

Results testing baseline - Estimted sells¶

5. Optimización del Modelo¶

6. Conclusiones¶

Anexo: Generación de Archivo Submit de la Competencia¶

Link de repositorio de GitHub: `https://github.com/josebarross/laboratorio-programacion`¶